Skip to main content
Glama

知你AI助手｜多平台客户与客服数据 MCP

by io.github.zhinikefu
OverviewDiscussionsAdmin

Server Details

汇聚个微、企微、视频号、微信小程序、公众号、服务号、微信客服、微信小店、抖音号、小红书、微博、网站及H5客服的客户资料、会话与聊天记录，供AI查询分析、会话研判与受确认的客户触达。

Ownership verified

The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Uptime
36.7% over 42 days
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP
URL
Repository
zhinikefu/zhini-ai-assistant-mcp
GitHub Stars
0
Server Listing
知你AI助手 MCP

TDQS

A4.4/5.0

Scored across 12 tools

Disambiguation4/5

Each tool targets a distinct resource and action, and descriptions go to unusual lengths to define boundaries (e.g. active vs. historical sessions, list vs. search for tags). The only genuinely confusable pairs are zhini_list_tags vs. zhini_search_tags and zhini_get_current_kefu vs. zhini_list_kefu, but the descriptions explicitly steer between them.

Naming Consistency5/5

Every tool uses the uniform zhini_ prefix followed by a lowercase snake_case verb_noun pattern (fetch/get/list/search + resource). The verbs are semantically appropriate and consistent across read operations, with no style mixing.

Tool Count5/5

12 tools is well within the ideal 3-15 range and each maps to a clear facet of the domain (messages, sessions, customers, tags, channels, agents, API quota). No redundant or filler tools are present.

Completeness4/5

The read/query lifecycle is well covered: locate customers, resolve their IDs, search sessions, read messages, and resolve tags/channels/agents. Gaps exist around write operations (message replies, session assignment, customer/tag edits), though the descriptions frame these as intentionally read-only, so it is largely complete for a query surface.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 12 tool updates
    • First observedzhini_fetch_messages
    • First observedzhini_get_apikey_usage
    • First observedzhini_get_current_kefu
    • First observedzhini_get_customer_profile
    • First observedzhini_list_active_sessions
    • First observedzhini_list_channels
    • First observedzhini_list_kefu
    • First observedzhini_list_tag_groups
    • First observedzhini_list_tags
    • First observedzhini_search_customers
    • First observedzhini_search_sessions
    • First observedzhini_search_tags

Related MCP Connectors

Related MCP Servers

Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources